{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0135464643727987,
  "eval_steps": 9,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000270929287455974,
      "grad_norm": 1.0075852870941162,
      "learning_rate": 1e-05,
      "loss": 4.6362,
      "step": 1
    },
    {
      "epoch": 0.000270929287455974,
      "eval_loss": 2.204838991165161,
      "eval_runtime": 232.8963,
      "eval_samples_per_second": 13.345,
      "eval_steps_per_second": 1.67,
      "step": 1
    },
    {
      "epoch": 0.000541858574911948,
      "grad_norm": 0.7891753911972046,
      "learning_rate": 2e-05,
      "loss": 3.9172,
      "step": 2
    },
    {
      "epoch": 0.000812787862367922,
      "grad_norm": 0.9741008281707764,
      "learning_rate": 3e-05,
      "loss": 4.7505,
      "step": 3
    },
    {
      "epoch": 0.001083717149823896,
      "grad_norm": 0.90495365858078,
      "learning_rate": 4e-05,
      "loss": 4.4032,
      "step": 4
    },
    {
      "epoch": 0.00135464643727987,
      "grad_norm": 1.0100457668304443,
      "learning_rate": 5e-05,
      "loss": 4.5474,
      "step": 5
    },
    {
      "epoch": 0.001625575724735844,
      "grad_norm": 0.9469624757766724,
      "learning_rate": 6e-05,
      "loss": 4.1974,
      "step": 6
    },
    {
      "epoch": 0.001896505012191818,
      "grad_norm": 1.2900989055633545,
      "learning_rate": 7e-05,
      "loss": 4.356,
      "step": 7
    },
    {
      "epoch": 0.002167434299647792,
      "grad_norm": 1.331476092338562,
      "learning_rate": 8e-05,
      "loss": 4.3353,
      "step": 8
    },
    {
      "epoch": 0.002438363587103766,
      "grad_norm": 1.0620654821395874,
      "learning_rate": 9e-05,
      "loss": 4.1061,
      "step": 9
    },
    {
      "epoch": 0.002438363587103766,
      "eval_loss": 2.091578722000122,
      "eval_runtime": 234.1485,
      "eval_samples_per_second": 13.274,
      "eval_steps_per_second": 1.661,
      "step": 9
    },
    {
      "epoch": 0.00270929287455974,
      "grad_norm": 1.3079955577850342,
      "learning_rate": 0.0001,
      "loss": 3.7498,
      "step": 10
    },
    {
      "epoch": 0.002980222162015714,
      "grad_norm": 1.1652690172195435,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.782,
      "step": 11
    },
    {
      "epoch": 0.003251151449471688,
      "grad_norm": 1.0940849781036377,
      "learning_rate": 9.987820251299122e-05,
      "loss": 4.314,
      "step": 12
    },
    {
      "epoch": 0.003522080736927662,
      "grad_norm": 0.8360046148300171,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.4797,
      "step": 13
    },
    {
      "epoch": 0.003793010024383636,
      "grad_norm": 1.2037752866744995,
      "learning_rate": 9.951340343707852e-05,
      "loss": 3.7035,
      "step": 14
    },
    {
      "epoch": 0.00406393931183961,
      "grad_norm": 1.4434421062469482,
      "learning_rate": 9.924038765061042e-05,
      "loss": 3.7721,
      "step": 15
    },
    {
      "epoch": 0.004334868599295584,
      "grad_norm": 1.6885652542114258,
      "learning_rate": 9.890738003669029e-05,
      "loss": 3.9332,
      "step": 16
    },
    {
      "epoch": 0.004605797886751558,
      "grad_norm": 1.7948238849639893,
      "learning_rate": 9.851478631379982e-05,
      "loss": 3.467,
      "step": 17
    },
    {
      "epoch": 0.004876727174207532,
      "grad_norm": 1.9752076864242554,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.9104,
      "step": 18
    },
    {
      "epoch": 0.004876727174207532,
      "eval_loss": 1.873294472694397,
      "eval_runtime": 233.735,
      "eval_samples_per_second": 13.297,
      "eval_steps_per_second": 1.664,
      "step": 18
    },
    {
      "epoch": 0.005147656461663506,
      "grad_norm": 2.20110821723938,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.4929,
      "step": 19
    },
    {
      "epoch": 0.00541858574911948,
      "grad_norm": 1.6183526515960693,
      "learning_rate": 9.698463103929542e-05,
      "loss": 3.768,
      "step": 20
    },
    {
      "epoch": 0.005689515036575454,
      "grad_norm": 1.4906808137893677,
      "learning_rate": 9.635919272833938e-05,
      "loss": 4.0027,
      "step": 21
    },
    {
      "epoch": 0.005960444324031428,
      "grad_norm": 1.279463529586792,
      "learning_rate": 9.567727288213005e-05,
      "loss": 3.181,
      "step": 22
    },
    {
      "epoch": 0.006231373611487402,
      "grad_norm": 1.5670361518859863,
      "learning_rate": 9.493970231495835e-05,
      "loss": 3.6572,
      "step": 23
    },
    {
      "epoch": 0.006502302898943376,
      "grad_norm": 1.7471691370010376,
      "learning_rate": 9.414737964294636e-05,
      "loss": 3.8337,
      "step": 24
    },
    {
      "epoch": 0.00677323218639935,
      "grad_norm": 1.6388347148895264,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.8581,
      "step": 25
    },
    {
      "epoch": 0.007044161473855324,
      "grad_norm": 1.5806576013565063,
      "learning_rate": 9.24024048078213e-05,
      "loss": 3.7995,
      "step": 26
    },
    {
      "epoch": 0.007315090761311298,
      "grad_norm": 1.4929829835891724,
      "learning_rate": 9.145187862775209e-05,
      "loss": 3.9813,
      "step": 27
    },
    {
      "epoch": 0.007315090761311298,
      "eval_loss": 1.7370423078536987,
      "eval_runtime": 233.8325,
      "eval_samples_per_second": 13.292,
      "eval_steps_per_second": 1.664,
      "step": 27
    },
    {
      "epoch": 0.007586020048767272,
      "grad_norm": 1.6387741565704346,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.6443,
      "step": 28
    },
    {
      "epoch": 0.007856949336223246,
      "grad_norm": 1.9017878770828247,
      "learning_rate": 8.940053768033609e-05,
      "loss": 4.1088,
      "step": 29
    },
    {
      "epoch": 0.00812787862367922,
      "grad_norm": 1.892134428024292,
      "learning_rate": 8.83022221559489e-05,
      "loss": 3.7689,
      "step": 30
    },
    {
      "epoch": 0.008398807911135195,
      "grad_norm": 1.6073269844055176,
      "learning_rate": 8.715724127386972e-05,
      "loss": 3.5192,
      "step": 31
    },
    {
      "epoch": 0.008669737198591168,
      "grad_norm": 1.9570190906524658,
      "learning_rate": 8.596699001693255e-05,
      "loss": 3.852,
      "step": 32
    },
    {
      "epoch": 0.008940666486047142,
      "grad_norm": 1.5949461460113525,
      "learning_rate": 8.473291852294987e-05,
      "loss": 3.4371,
      "step": 33
    },
    {
      "epoch": 0.009211595773503115,
      "grad_norm": 1.2864899635314941,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.9907,
      "step": 34
    },
    {
      "epoch": 0.00948252506095909,
      "grad_norm": 1.1819583177566528,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.6687,
      "step": 35
    },
    {
      "epoch": 0.009753454348415064,
      "grad_norm": 1.6467957496643066,
      "learning_rate": 8.07830737662829e-05,
      "loss": 3.2719,
      "step": 36
    },
    {
      "epoch": 0.009753454348415064,
      "eval_loss": 1.6752654314041138,
      "eval_runtime": 233.8576,
      "eval_samples_per_second": 13.29,
      "eval_steps_per_second": 1.663,
      "step": 36
    },
    {
      "epoch": 0.010024383635871038,
      "grad_norm": 1.2391555309295654,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.0545,
      "step": 37
    },
    {
      "epoch": 0.010295312923327011,
      "grad_norm": 1.87485933303833,
      "learning_rate": 7.795964517353735e-05,
      "loss": 3.2457,
      "step": 38
    },
    {
      "epoch": 0.010566242210782985,
      "grad_norm": 1.3642981052398682,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.9937,
      "step": 39
    },
    {
      "epoch": 0.01083717149823896,
      "grad_norm": 2.1650807857513428,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.3383,
      "step": 40
    },
    {
      "epoch": 0.011108100785694934,
      "grad_norm": 1.1839669942855835,
      "learning_rate": 7.347357813929454e-05,
      "loss": 3.3796,
      "step": 41
    },
    {
      "epoch": 0.011379030073150907,
      "grad_norm": 1.4667418003082275,
      "learning_rate": 7.191855733945387e-05,
      "loss": 3.1791,
      "step": 42
    },
    {
      "epoch": 0.01164995936060688,
      "grad_norm": 2.1223866939544678,
      "learning_rate": 7.033683215379002e-05,
      "loss": 3.541,
      "step": 43
    },
    {
      "epoch": 0.011920888648062856,
      "grad_norm": 1.6458444595336914,
      "learning_rate": 6.873032967079561e-05,
      "loss": 3.2844,
      "step": 44
    },
    {
      "epoch": 0.01219181793551883,
      "grad_norm": 1.5712699890136719,
      "learning_rate": 6.710100716628344e-05,
      "loss": 3.2106,
      "step": 45
    },
    {
      "epoch": 0.01219181793551883,
      "eval_loss": 1.638505220413208,
      "eval_runtime": 234.0386,
      "eval_samples_per_second": 13.28,
      "eval_steps_per_second": 1.662,
      "step": 45
    },
    {
      "epoch": 0.012462747222974803,
      "grad_norm": 1.6857413053512573,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.5275,
      "step": 46
    },
    {
      "epoch": 0.012733676510430777,
      "grad_norm": 2.234515905380249,
      "learning_rate": 6.378186779084995e-05,
      "loss": 3.6425,
      "step": 47
    },
    {
      "epoch": 0.013004605797886752,
      "grad_norm": 1.8203272819519043,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.9848,
      "step": 48
    },
    {
      "epoch": 0.013275535085342726,
      "grad_norm": 2.177682399749756,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 3.8714,
      "step": 49
    },
    {
      "epoch": 0.0135464643727987,
      "grad_norm": 1.284415364265442,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.8472,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.474786561589248e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}